Duration distribution based HMM speech recognition models

Tien Tzu Hsueh Pao/Acta Electronica Sinica

Volumn 32, Issue 1, 2004, Pages 46-49

  Wang, Zuo Ying ^a   Xiao, Xi ^a  

^a TSINGHUA UNIVERSITY   (China)

Author keywords

DDBHMM; Duration; Speech recognition

Indexed keywords

MARKOV PROCESSES; MATHEMATICAL MODELS; PROBABILITY;

DURATION DISTRIBUTION; HIDDEN MARKOV MODELS; INTER FRAME CORRELATION; SPEECH DISCONTINUITY; SPEECH VARIATION; STATE DURATION; STATE TRANSITION PROBABILITY;

SPEECH RECOGNITION;

EID: 2342443171     PISSN: 03722112     EISSN: None     Source Type: Journal    
DOI: None     Document Type: Article

References (19)

1. Rabiner L R. A tutorial on hidden Markov models and selected applications in speech recognition [J]. Proceedings of the IEEE, 1989, 77(2): 257-286.
2. S E Levision, L R Rabiner, M M Sondhi. An introduction to the application of the theory of probabilistic functions of a markov process to automatic speech recognition [J]. The Bell System Technical Journal, April 1983, 62(4): 1035-1074.
3. Burshtein D. Robust parametric modeling of durations in hidden Markov models [A]. Proceedings of IEEE ICASSP [C]. Detroit, MI, USA, ICASSP-95, 1995. 1: 548-551.
4. Wei-wen HUNG, Hsiao-chuan WANG. Improvement of noisy speech recognition using a proportional alignment decoding algorithm in the training phase [J]. Computer Speech and Language, 1998, 12(3): 165-192.
5. J D Ferguson. Variable duration models for speech [A]. Proc. of Symposium on the Application of Hidden Markov Models to Text and Speech [C]. Princeton, New Jersey: Institute for Defense Analyses Communications Research Division, 1980. 143-179.
6. S E Levinson. Continuously variable duration hidden markov models for automatic speech recognition [J]. Computer Speech and Language, 1986, 1: 29-45.
7. M J Russell, R K Moore. Explicit modeling of state occupancy in Hidden Markov Models for automatic speech recognition [A]. Proceedings of IEEE ICASSP [C]. ICASSP-85, Tampa, Florida, USA, 1985. 5-8.
8. Ratnayake N, Savic M, Sorensen J. Use of semi-Markov models for speaker-independent phoneme recognition [A]. Proceedings of IEEE ICASSP [C]. San Francisco, CA, USA, ICASSP-92, 1992, 1. 565-568.
9. Mitchell C D, Jamieson L H. Modeling duration in a hidden Markov model with the exponential family [A]. Proceedings of IEEE ICASSP [C]. Minneapolis, MN, USA, ICASSP-93, 1993, 2. 331-334.
10. Martin J Russel, Anneliese E Cook. Experimental Evaluation of Duration Modeling Techniques for Automatic Speech Recognition [A]. Proceedings of IEEE ICASSP [C]. ICASSP-87, Dallas, USA, 1987. 2376-2379.
11. Bonafonte A, Vidal J, Nogueiras A. Duration modeling with expanded HMM applied to speech recognition [A]. Proceedings of the Fourth International Conference on Spoken Language, Philadelphia [C]. PA, USA, ICSLP 96, 1996, 2. 1097-1100.
12. Ramesh P, Wilpon J G. Modeling state durations in hidden Markov models for automatic speech recognition [A]. Proceedings of IEEE ICASSP [C]. San Francisco, CA, USA, ICASSP-92, 1992, 1. 381-384.
13. S V Vaseghi. Hidden Markov models with duration-dependent state transition probabilities [J]. Electronics Letters, 1991, 27(8): 625-626.
14. Vaseghi. State duration modeling in hidden Markov models [J]. Signal Processing, 1995, 41: 31-41.
15. Ostendorf M, Digalakis V V, Kimball O A. From HMM's to segment models: a unified view of stochastic modeling for speech recognition [J]. IEEE Transactions on Speech and Audio Processing, Sept. 1996, 4(5): 360-378.
16. Zuo-ying WANG, Hong-ge GAO. An inhomogeneous HMM speech recognition algorithm [J]. Chinese Journal of Electronics, January 1998, 7(l): 73-77.
17. Neri Merhav, Yariv Ephraim. Hidden Markov Modeling Using the Most Likely State Sequence [A]. Proceedings of IEEE ICASSP [C]. Toronto, Ont., Canada, ICASSP-91, 1991, 1. 469-472.